Papers › DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation
DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation
Zilu Guo, Liuyang Bian, Xuan Huang, Hu Wei, Jingyu Li, Huasheng Ni
Atrous convolutions are employed as a method to increase the receptive field in semantic segmentation tasks. However, in previous works of semantic segmentation, it was rarely employed in the shallow layers of the model. We revisit the design of atrous convolutions in modern convolutional neural networks (CNNs), and demonstrate that the concept of using large kernels to apply atrous convolutions could be a more powerful paradigm. We propose three guidelines to apply atrous convolutions more efficiently. Following these guidelines, we propose DSNet, a Dual-Branch CNN architecture, which incorporates atrous convolutions in the shallow layers of the model architecture, as well as pretraining the nearly entire encoder on ImageNet to achieve better performance. To demonstrate the effectiveness of our approach, our models achieve a new state-of-the-art trade-off between accuracy and speed on ADE20K, Cityscapes and BDD datasets. Specifically, DSNet achieves 40.0% mIOU with inference speed of 179.2 FPS on ADE20K, and 80.4% mIOU with speed of 81.9 FPS on Cityscapes. Source code and models are available at Github: https://github.com/takaniwa/DSNet.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Real-Time Semantic Segmentation | Cityscapes val | DSNet | Frame (fps) | 81.9 | #2 of 24 | Archive leaderboard | report |
| Real-Time Semantic Segmentation | Cityscapes val | DSNet | mIoU | 80.4% | #2 of 24 | Archive leaderboard | report |
| Semantic Segmentation | BDD100K val | DSNet-Base | mIoU | 64.6 | #3 of 24 | Archive leaderboard | report |
| Semantic Segmentation | BDD100K val | DSNet-head64 | mIoU | 62.6(172.2FPS 4090) | #24 of 24 | Archive leaderboard | report |
| Semantic Segmentation | CamVid | DSNet-Base | Mean IoU | 83.32 | #3 of 21 | Archive leaderboard | report |
| Semantic Segmentation | Cityscapes val | DSNet-Base(single-scale) | mIoU | 82.0 | #38 of 99 | Archive leaderboard | report |
| Semantic Segmentation | Cityscapes val | DSNet(single-scale) | FPS | 81.9 | #50 of 99 | Archive leaderboard | report |
| Semantic Segmentation | Cityscapes val | DSNet(single-scale) | mIoU | 80.4 | #50 of 99 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections